MCP Server DevOps Bridge 🚀
About
# MCP Server DevOps Bridge 🚀 > Connect your DevOps tools with the power of AI This project evolved from a simple experiment into a powerful bridge between your essential DevOps platforms, providing a unified interface through Claude and other AI assistants. With integrated agent capabilities, it can even delegate work…
Details
- License
- MIT license
Explore
- Status Report Generation
- Combine data from multiple sources
- Sprint status reports
- Work item summaries
- PR status integration
- Work Item Reminders
- Slack notifications
- Customizable messages
- Automated tracking
- Standup Report Generation
- Team-based reporting
- State-grouped work items
- Rich Slack formatting
export EMAIL_INBOX_WEBHOOK_URL="YOUR WEBHOOK URL"
export EMAIL_SEARCH_WEBHOOK_URL="YOUR WEBHOOK URL"
export EMAIL_REPLY_WEBHOOK_URL="YOUR WEBHOOK URL"
/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge
```
- Go 1.23.4 or later
- Docker (required for agent system)
- Access tokens for your platforms:
- Azure DevOps PAT
- GitHub PAT (optional)
- Slack Bot Token (optional)
- OpenAI API Key (for agents)
If you don't have direct access to modify environment variables, create a start.sh script and make it executable:
#!/bin/bash
export AZURE_DEVOPS_ORG="YOUR ORG"
export AZDO_PAT="YOUR PAT"
export AZURE_DEVOPS_PROJECT="YOUR PROJECT"
export GITHUB_PAT="YOUR PAT"
export SLACK_BOT_TOKEN="YOUR TOKEN"
export DEFAULT_SLACK_CHANNEL="YOUR CHANNEL ID"
export OPENAI_API_KEY="YOUR API KEY"
export QDRANT_URL="http://localhost:6333"
export QDRANT_API_KEY="your-qdrant-api-key"
export NEO4J_URL="http://localhost:7474"
export NEO4J_USER="neo4j"
export NEO4J_PASSWORD="your-neo4j-password"
export EMAIL_INBOX_WEBHOOK_URL="YOUR WEBHOOK URL"
export EMAIL_SEARCH_WEBHOOK_URL="YOUR WEBHOOK URL"
export EMAIL_REPLY_WEBHOOK_URL="YOUR WEBHOOK URL"
/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge
Connect your essential DevOps platforms with a natural language interface:
- Azure DevOps - Work items, wiki, sprints, and project management
- GitHub - Pull requests, code reviews, repositories
- Slack - Team communication, notifications, updates
- Browser Automation - Web interactions, screenshots, JavaScript execution
- AI Agents - Delegate tasks to autonomous AI agents
The system provides tools for:
- Command Execution: Run system commands with proper security controls
- Messaging: Send and receive messages between agents
- Agent Management: Create, monitor, and terminate agents
> Connect your DevOps tools with the power of AI
This project evolved from a simple experiment into a powerful bridge between your essential DevOps platforms, providing a unified interface through Claude and other AI assistants. With integrated agent capabilities, it can even delegate work autonomously!
🌉 Bridge Your DevOps Tools
Connect your essential DevOps platforms with a natural language interface:
- Azure DevOps - Work items, wiki, sprints, and project management
- GitHub - Pull requests, code reviews, repositories
- Slack - Team communication, notifications, updates
- Browser Automation - Web interactions, screenshots, JavaScript execution
- AI Agents - Delegate tasks to autonomous AI agents
🎯 Key Benefits
- Natural Language Interface - Interact with your tools using plain English
- Cross-Platform Integration - Work items link to PRs, PRs trigger notifications
- Unified Workflow - Let AI handle the context switching between tools
- Flexible Architecture - Easy to extend with new integrations
- Autonomous Workflows - Create AI agents to handle repetitive tasks
🚀 Getting Started
Prerequisites
- Go 1.23.4 or later
- Docker (required for agent system)
- Access tokens for your platforms:
- Azure DevOps PAT
- GitHub PAT (optional)
- Slack Bot Token (optional)
- OpenAI API Key (for agents)
Installation
1. Clone and build:
git clone https://github.com/theapemachine/mcp-server-devops-bridge
cd mcp-server-devops-bridge
go build
2. Configure your environment:
```bash
export AZURE_DEVOPS_ORG="your-org"
export AZDO_PAT="your-pat-token"
export AZURE_DEVOPS_PROJECT="your-project"
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
